Joakim Tjernlund [Fri, 19 Nov 2010 13:15:33 +0000 (14:15 +0100)]
mpc83xx: Make it boot again
After the removal of COLD/WARM start flags my mpc8321
board didn't boot anymore.
Trial and error suggests that map/remap_flash_by_xxx needs
to wait after updating LBLAWAR1 to make sure the the change has
reached the HW before continuing with the code that depends on it.
Final fix suggested by Scott Wood.
Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se> Acked-by: Scott Wood <scottwood@freescale.com> Signed-off-by: Kim Phillips <kim.phillips@freescale.com>
----
arch/sh/cpu/sh4/libsh4.o: In function `_start':
(.text+0x204): multiple definition of `_start'
arch/sh/cpu/sh4/start.o:(.text+0x0): first defined here
----
cfi_flash: fix bug introduced while recent change to flash_get_size()
commit ec50a8e389863ac35bfd9d9a2e8b30187318e59e
"cfi_flash: handle 'chip size exceeds address window' situation"
added 3rd argument to flash_get_size() but didn't fix all the
function calls from the board specific code. Many boards have
their own flash_get_size() definitions in the board code and
use them there, but some boards (e.g. tqm834x, tqm85xx, pdm360ng)
use flash_get_size() from the cfi_flash.c driver.
The bug shows up if the value of the "max_size" argument (which
is not defined when calling the function with two arguments)
happens to be less than "info->size". In this case on the
affected boards we end up with a bank of reduced size and
in the worst case might even be not able to update U-Boot or
to boot the kernel from flash:
=> fli
Bank # 1: CFI conformant FLASH (32 x 16) Size: 0 kB in 1 Sectors
AMD Standard command set, Manufacturer ID: 0x01, Device ID: 0x227E
Erase timeout: 4096 ms, write timeout: 1 ms
Buffer write timeout: 3 ms, buffer size: 64 bytes
=> protect off ${u-boot_addr} +${u-boot_size}
Error: end address (0xf007ffff) not in flash!
Bad address format
=> era ${u-boot_addr} +${u-boot_size}
Error: end address (0xf007ffff) not in flash!
Bad address format
This patch removes the 3rd argument of flash_get_size() again
and sets "max_size" in the function itself instead of passing
it as a function argument.
Dirk Behme [Sun, 21 Nov 2010 19:19:34 +0000 (20:19 +0100)]
Fix compiler warning in fdt_support.c
Fix compiler warning
fdt_support.c: In function 'of_bus_default_count_cells':
fdt_support.c:957: warning: passing argument 1 of '__swab32p' discards qualifiers from pointer target type
fdt_support.c:965: warning: passing argument 1 of '__swab32p' discards qualifiers from pointer target type
be32_to_cpup() expects an 'u32 *' while prop is 'const u32 *'.
Stefan Roese [Fri, 26 Nov 2010 14:45:34 +0000 (15:45 +0100)]
ppc4xx: Flush complete dcache in relocate_code()
When the cache is enabled in SDRAM we need to flush not only the global
data area but also the bd_info struct in relocate_code. This patch now
flushed the complete dcache (all dcache lines) via flush_dcache() instead
of adding a flush_dcache_range() call for bd_info since this is faster.
Stefan Roese [Fri, 26 Nov 2010 14:45:22 +0000 (15:45 +0100)]
ppc4xx/POST: Handle cached SDRAM correctly in Denali (440EPx) ECC POST
This patch fixes a problem in the Denali (440EPx) SDRAM ECC POST test.
When cache is enabled in the SDRAM area, the values written to SDRAM
need to be flushed from cache to SDRAM using the dcfb instruction.
Without this patch the POST ECC test failed. Now its working again on
platforms with cache enabled in SDRAM.
Wolfgang Denk [Mon, 22 Nov 2010 22:36:42 +0000 (23:36 +0100)]
512x: Cleanup for partial linking and --gc-sections
Signed-off-by: Wolfgang Denk <wd@denx.de> Cc: Anatolij Gustschin <agust@denx.de> Cc: Timur Tabi <timur@freescale.com> Acked-by: Stefan Roese <sr@denx.de>
Stefan Roese [Tue, 23 Nov 2010 13:32:48 +0000 (14:32 +0100)]
ppc4xx/NAND: Reduce size of NAND SPL image
This is needed for the canyonlands_nand build target. Without it
the resulting image won't fit into 4k.
Signed-off-by: Stefan Roese <sr@denx.de> Cc: Scott Wood <scottwood@freescale.com> Acked-by: Scott Wood <scottwood@freescale.com> Acked-by: Stefan Roese <sr@denx.de>
Wolfgang Denk [Sun, 21 Nov 2010 19:55:42 +0000 (20:55 +0100)]
ppc4xx: Cleanup for partial linking and --gc-sections
This commit adapts 4xx boards for partial linking with --gc-sections.
Signed-off-by: Stefan Roese <sr@denx.de> Signed-off-by: Wolfgang Denk <wd@denx.de> Cc: Stefan Roese <sr@denx.de> Cc: Tirumala Marri <tmarri@apm.com> Cc: David Updegraff <dave@cray.com> Cc: Matthias Fuchs <matthias.fuchs@esd-electronics.com> Cc: Dirk Eibach <eibach@gdsys.de> Cc: Larry Johnson <lrj@acm.org> Cc: Peter De Schrijver <p2@mind.be> Cc: Niklaus Giger <niklaus.giger@netstal.com> Cc: Daniel Poirot <dan.poirot@windriver.com> Acked-by: Stefan Roese <sr@denx.de>
Wolfgang Denk [Sun, 21 Nov 2010 19:46:02 +0000 (20:46 +0100)]
POWERPC: enable --gc-sections and -ffunction-sections -fdata-sections
The switch from archive libraries to partial linking has introduced a
number of problems, that are non-trivial to solve. For example, it is
no longer possible to include individual object files in the linker
script as we did before for example in the case of boards with
embedded environment to fill up the gap caused by the need to align
the environment on flash erase block boundaries.
The best (but unfortunately not easiest) approach to address this
problem is to enable -ffunction-sections (and -fdata-sections) so
we can again (and even in much finer granularity) place certain code
where we want it. When doing this step, it seems only consequent to
also add --gc-sections which has the added benefit of reducing the
memory footprint of the U-Boot image (both in flash and in RAM).
Unfortunately, this requires changes to a lot of linker scripts.
Signed-off-by: Wolfgang Denk <wd@denx.de> Cc: Stefan Roese <sr@denx.de> Cc: Kim Phillips <kim.phillips@freescale.com> Cc: Andy Fleming <afleming@gmail.com> Cc: Kumar Gala <galak@kernel.crashing.org> Acked-by: Stefan Roese <sr@denx.de>
Without this, NAND SPLs are built with the text base intended for the main
image, resulting in a broken, very large u-boot-nand.bin.
The block of defines for NAND boot is moved closer to where
CONFIG_SYS_TEXT_BASE is defined. We can't directly use
CONFIG_SYS_NAND_U_BOOT_DST in the definition of CONFIG_SYS_TEXT_BASE because
autoconf.mk will include the literal text "CONFIG_SYS_NAND_U_BOOT_DST",
but at least keep them close and point out that they're supposed to be
the same.
Signed-off-by: Scott Wood <scottwood@freescale.com>
Wolfgang Denk [Sun, 21 Nov 2010 16:04:17 +0000 (17:04 +0100)]
PPChameleonEVB and CATcenter need a custom linker script
These boards use an embedded environment, which is not supported by the
generic arch/powerpc/cpu/ppc4xx/u-boot.lds script.
The breakage was introduced by commit 2cd95a2 "ppc4xx: Remove board
specific linker scripts from most PPC4xx boards"
Signed-off-by: Wolfgang Denk <wd@denx.de> Cc: Stefan Roese <sr@denx.de> Cc: Andrea Marson <andrea.marson@dave-tech.it> Acked-by: Stefan Roese <sr@denx.de>
Wolfgang Denk [Sun, 21 Nov 2010 15:34:05 +0000 (16:34 +0100)]
arch/powerpc/*/config.mk: make CONFIG_SYS_LDSCRIPT settings work
As we try to get rid of board specific config.mk files we must
provide a way for board specific settings of the LDSCRIPT variable
(path to the linker script) where needed.
We now implement the following hierarchy:
- Highest priority has a "#define CONFIG_SYS_LDCONFIG" in the board
config file.
- If CONFIG_SYS_LDCONFIG is not set, and the system is booting from
NAND (CONFIG_NAND_SPL is set), then a board specific linker
script board/$(BOARDDIR)/u-boot-nand.lds gets used.
- If we are not booting from NAND, we test if a processor specific
linker script arch/powerpc/cpu/$(CPU)/u-boot.lds exists; if so we
use that.
- As default, arch/powerpc/config.mk gets used.
Signed-off-by: Wolfgang Denk <wd@denx.de> Cc: Stefan Roese <sr@denx.de> Cc: Kim Phillips <kim.phillips@freescale.com> Cc: Kumar Gala <kumar.gala@freescale.com> Cc: Andy Fleming <afleming@gmail.com> Acked-by: Stefan Roese <sr@denx.de>
Wolfgang Denk [Sat, 20 Nov 2010 14:04:02 +0000 (15:04 +0100)]
common/Makefile: don't include env_embedded.o into libcommon
Some boards use an embedded environment, where env_embedded.o has to
be linked at a special position in the U-Boot image; to make this
possible, we do not include it into libcommon.o for such boards.
Signed-off-by: Mike Frysinger <vapier@gentoo.org> Signed-off-by: Wolfgang Denk <wd@denx.de> Acked-by: Stefan Roese <sr@denx.de>
Wolfgang Denk [Wed, 24 Nov 2010 21:27:08 +0000 (22:27 +0100)]
cam5200_niosflash: fix build warnings
Fix warnings:
cam5200_flash.c: In function 'write_word_32':
cam5200_flash.c:443: warning: dereferencing type-punned pointer will break strict-aliasing rules
cam5200_flash.c: In function 'write_word_16':
cam5200_flash.c:684: warning: dereferencing type-punned pointer will break strict-aliasing rules
Signed-off-by: Wolfgang Denk <wd@denx.de> Acked-by: Stefan Roese <sr@denx.de>
Wolfgang Denk [Tue, 23 Nov 2010 22:17:18 +0000 (23:17 +0100)]
WINBOND_83C553: enable only on boards that actually use it.
So far, only the BAB7xx board would call the initialise_w83c553f()
function for the WINBOND 83C553 chip, even though some other boards
(HIDDEN_DRAGON, Sandpoint8240, Sandpoint8245) enabled it in their
board configuration. These boards were also missing other config
settings needed for that, which resulted in build errors like this:
drivers/pci/libpci.o:(.got2+0x84): undefined reference to `ide_bus_offset'
Switch arch/powerpc/lib/board.c to call initialise_w83c553f() not on a
per-board base, but when a WINBOND_83C553 in enabled in a
configuration (like BAB7xx), and disable it in the boards that had
this set so far.
Signed-off-by: Wolfgang Denk <wd@denx.de> Cc: Yusdi Santoso <yusdi_santoso@adaptec.com> Cc: Jim Thompson <jim@musenki.com> Acked-by: Stefan Roese <sr@denx.de>
Wolfgang Denk [Mon, 22 Nov 2010 08:48:45 +0000 (09:48 +0100)]
e1000: fix compile warning
Get rid of compiler warning:
e1000.c: In function 'e1000_transmit':
e1000.c:5028: warning: passing argument 1 of 'virt_to_phys' discards qualifiers from pointer target type
Signed-off-by: Wolfgang Denk <wd@denx.de> Acked-by: Stefan Roese <sr@denx.de>
Wolfgang Denk [Sun, 21 Nov 2010 19:40:23 +0000 (20:40 +0100)]
ERIC: drop unsupported board configuration
The ERIC board appears to be unmaintained for more than 9 years. The
environment location has probably never been correct, and has been
definitely broken since for at least a year. Drop it.
Signed-off-by: Wolfgang Denk <wd@denx.de> Cc: Stefan Roese <sr@denx.de> Cc: Swen Anderson <sand@peppercon.de> Acked-by: Stefan Roese <sr@denx.de>
Stefan Roese [Fri, 26 Nov 2010 14:43:44 +0000 (15:43 +0100)]
usb: Remove usb_dev_init() from ehci-ppc4xx.c
Calling usb_dev_init() from within the EHCI host driver is wrong.
The EHCI host driver should have no dependency/interconnection to the
USB device driver.
Signed-off-by: Stefan Roese <sr@denx.de> Cc: Remy Bohmer <linux@bohmer.net>
Stefan Roese [Fri, 26 Nov 2010 14:44:00 +0000 (15:44 +0100)]
usb: Clear CMD_RUN while issuing CMD_RESET in ehci_reset()
This patch fixes a problem noticed on lwmon5 (PPC440EPx) using the
common EHCI driver, when "usb reset" is issued multiple times.
Upon the 2nd (and further) "usb reset" command, the command fails
with the following messages:
=> usb reset
(Re)start USB...
USB: Register 1111 NbrPorts 1
USB EHCI 1.00
scanning bus for devices... 5 USB Device(s) found
scanning bus for storage devices... 2 Storage Device(s) found
=> usb reset
(Re)start USB...
USB: EHCI fail to reset
Error, couldn't init Lowlevel part
This patch fixes this problem. Now "usb reset" can be called multiple
times.
Signed-off-by: Stefan Roese <sr@denx.de> Cc: Remy Bohmer <linux@bohmer.net>
usb: fix for USB_ST_STALLED status reporting in ehci_submit_async()
Checking the status field of the qTD token in the current code
do not take into acount cases where endpoint stall (halted) bit
is set together with XactErr status bit. As a result clearing
stall on an endpoint won't be done if this status bit was also
set. Check for halted bit and report USB_ST_STALLED status
if the host controller also indicates endpoit stall condition.
Eric Cooper [Wed, 24 Nov 2010 11:41:32 +0000 (17:11 +0530)]
Seagate FreeAgent DockStar support
start with sheevaplug configuration
add modifications by Alexander Holler <holler@ahsoftware.de>
change RAM definitions to one bank (128 MB)
change ident string and prompt
define MTD partitions and default environment variables
add support for LEDs
Mike Frysinger [Sat, 20 Nov 2010 00:28:56 +0000 (19:28 -0500)]
Blackfin: tweak objects specified before embedded environment
The partial linking patch changes how objects are specified to the linker
and breaks boards with an embedded environment. So we need to tweak the
list of objects we specify via the linker script that go in the gap before
the embedded env to work with this new behavior. This fixes linker errors
for all the boards in question.
Mike Frysinger [Sat, 20 Nov 2010 00:17:53 +0000 (19:17 -0500)]
Blackfin: drop initcode.o from combined object
We explicitly link in the initcode.o in the Blackfin linker script, so
there is no need to merge it into the main common object for the linker
to pull in itself. This also fixes duplicate symbol errors with the new
partial linking logic.
Sekhar Nori [Fri, 19 Nov 2010 16:39:48 +0000 (11:39 -0500)]
DA850 EVM: passing maximum clock rate information to kernel
The TI DA850/OMAP-L138/AM18x EVM can be populated with devices
having different maximum allowed CPU clock rating.
The maximum clock the chip can support can only be determined from
the label on the package (not software readable).
Introduce a method to pass the maximum allowed clock rate information
to kernel using ATAG_REVISION. The kernel uses this information to
determine the maximum cpu clock rate reachable using cpufreq.
Note that U-Boot itself does not set the CPU clock rate. The CPU
clock is setup by a primary bootloader ("UBL"). The rate setup by
UBL could be different from the maximum clock rate supported by the
device.
Signed-off-by: Sekhar Nori <nsekhar@ti.com> Signed-off-by: Sandeep Paulraj <s-paulraj@ti.com>
>From the commit message for "Switch from archive libraries to partial linking":
This commit reveals board configurations that exclude some features but
include source files that depend these disabled features in the build,
resulting in undefined symbols. Known such cases include:
- disabling CMD_NET but not CMD_NFS;
- enabling CONFIG_OF_LIBFDT but not CONFIG_QE.
Signed-off-by: Steve Sakoman <steve.sakoman@linaro.org> Signed-off-by: Sandeep Paulraj <s-paulraj@ti.com>
Update pandora's config so that it can boot production kernels from NAND.
This enables UBI, USB, sets up NAND layout and default boot command.
It also expands malloc area so that UBI works.
Most OMAP3 boards have various flash related macros in their configs
that are either not referenced anywhere in the code or are used by
drivers that are not enabled. Remove them.
Nishanth Menon [Fri, 19 Nov 2010 16:19:40 +0000 (11:19 -0500)]
omap4: board: change global data pointer to file scope
DECLARE_GLOBAL_DATA_PTR is currently defined within the scope
of function while it is a global pointer. Change the scope of
definition to replicate it's global scope. This seems to help
gcc 4.5 optimizations as well.
Nishanth Menon [Fri, 19 Nov 2010 16:18:12 +0000 (11:18 -0500)]
mmc: omap: timeout counter fix
Having a loop with a counter is no timing guarentee for timing
accuracy or compiler optimizations. For e.g. the same loop counter
which runs when the MPU is running at 600MHz will timeout in around
half the time when running at 1GHz. or the example where GCC 4.5
compiles with different optimization compared to GCC 4.4. use timer
to keep track of time elapse and we use an emperical number - 1sec
for a worst case timeout. This should never happen, and is adequate
imaginary condition for us to fail with timeout.
The da8xx fixup commit changed da830/da850 common code to make
relocation work in da850, but didn't add the required defines
to da830evm_config.h resulting in build failure in the common code.
This patch adds those defines for da830, but makes no sense without
also referring to the commit mentioned above.
Signed-off-by: Nick Thompson <nick.thompson@ge.com> Reviewed-by: Ben Gardiner <bengardiner@nanometrics.ca> Signed-off-by: Sandeep Paulraj <s-paulraj@ti.com>
Previously with archive libraries fdt.o was compiled and included in
qe.a and then discarded by the linker. With partial linking this
results in unresolved symbols, which this commit fixes.
This commit also cleans up a now-useless conditional in fdt.c.
Signed-off-by: Sebastien Carlier <sebastien.carlier@gmail.com> Tested-by: Wolfgang Denk <wd@denx.de>
Mike Frysinger [Mon, 15 Nov 2010 13:16:19 +0000 (08:16 -0500)]
Blackfin: make sure bss len is multiple of 4 bytes
The Blackfin on-chip BootROM requires that fill operations (which is
used for the bss) be aligned to 4 bytes (base addr and total len).
Plus, the Blackfin early init asm code assumes the same thing. So
rather than making things work for no real gain, make sure the bss
len is padded to 4 bytes in the linker script.
Kumar Gala [Tue, 16 Nov 2010 00:41:43 +0000 (18:41 -0600)]
malloc: Fix issue with calloc memory possibly being non-zero
Since we set #define MORECORE_CLEARS 1, the code assumes 'sbrk' always
returns zero'd out memory. However since its possible that free()
returns memory back to sbrk() via malloc_trim we could possible get
non-zero'd memory from sbrk(). This is a problem for when code might
call calloc() and expect the memory to have been zero'd out.
There are two possible solutions to this problem.
1. change #define MORECORE_CLEARS 0
2. memset to zero memory returned to sbrk.
We go with the second since the sbrk being called to free up memory
should be pretty rare.
The following code problems an example test to show the issue. This
test code was inserted right after the call to mem_malloc_init().
Before this commit, weak symbols were not overridden by non-weak symbols
found in archive libraries when linking with recent versions of
binutils. As stated in the System V ABI, "the link editor does not
extract archive members to resolve undefined weak symbols".
This commit changes all Makefiles to use partial linking (ld -r) instead
of creating library archives, which forces all symbols to participate in
linking, allowing non-weak symbols to override weak symbols as intended.
This approach is also used by Linux, from which the gmake function
cmd_link_o_target (defined in config.mk and used in all Makefiles) is
inspired.
The name of each former library archive is preserved except for
extensions which change from ".a" to ".o". This commit updates
references accordingly where needed, in particular in some linker
scripts.
This commit reveals board configurations that exclude some features but
include source files that depend these disabled features in the build,
resulting in undefined symbols. Known such cases include:
- disabling CMD_NET but not CMD_NFS;
- enabling CONFIG_OF_LIBFDT but not CONFIG_QE.
Albert Aribaud [Mon, 15 Nov 2010 20:46:04 +0000 (21:46 +0100)]
tx25: fix linker file for newer ld support
older ld emitted all ELF relocations in input sections named
.rel.dyn, whereas newer ld uses names of the form .rel*. The
linker script only collected .rel.dyn input sections. Rewrite
to collect all .rel* input sections.
Signed-off-by: Albert Aribaud <albert.aribaud@free.fr>
Albert Aribaud [Mon, 15 Nov 2010 20:46:03 +0000 (21:46 +0100)]
ARM: fix linker file for newer ld support
older ld emitted all ELF relocations in input sections named
.rel.dyn, whereas newer ld uses names of the form .rel*. The
linker script only collected .rel.dyn input sections. Rewrite
to collect all .rel* input sections.
Signed-off-by: Albert Aribaud <albert.aribaud@free.fr>
Heiko Schocher [Mon, 15 Nov 2010 07:20:39 +0000 (08:20 +0100)]
post, i2c: add missing curly bracket in i2c_post_test
If CONFIG_SYS_POST_I2C_ADDRS is not defined and CONFIG_SYS_POST_I2C
is activated, i2c_probe() is not called in the for statement,
because missing curly bracket.
Ben Warren [Wed, 1 Sep 2010 06:05:04 +0000 (23:05 -0700)]
Net: clarify board/cpu_eth_init calls
This has always been confusing, and the idea of these functions returning the
number of interfaces initialized was half-baked and ultimately pointless.
Instead, act more like regular functions and return < 0 on failure, >= 0 on
success.
This change shouldn't break anything.
Signed-off-by: Ben Warren <biggerbadderben@gmail.com>
Peter Tyser [Fri, 29 Oct 2010 22:59:06 +0000 (17:59 -0500)]
MAKEALL: Do a sanity check on user-supplied arguments
Add a check to make sure that the user's arguments actually find a board
in boards.cfg. Previously, if a user misspelled an argument the
argument would be discarded without warning. For example, running
'MAKEALL -c 85xx' with the intention of compiling all Freescale 85xx
boards would instead silently discard the '-c 85xx' argument since the
proper cpu name is 'mpc85xx' and then proceed to compile all PowerPC
boards (MAKEALL's default).
Peter Tyser [Fri, 29 Oct 2010 22:59:29 +0000 (17:59 -0500)]
pci: Use intelligent indentation for CONFIG_PCI_SCAN_SHOW
When CONFIG_PCI_SCAN_SHOW is defined U-Boot prints out PCI devices as
they are found during bootup, eg:
PCIE1: connected as Root Complex
01:00.0 - 10b5:8518 - Bridge device
02:01.0 - 10b5:8518 - Bridge device
03:00.0 - 10b5:8112 - Bridge device
04:01.0 - 8086:1010 - Network controller
04:01.1 - 8086:1010 - Network controller
02:02.0 - 10b5:8518 - Bridge device
02:03.0 - 10b5:8518 - Bridge device
06:00.0 - 10b5:8518 - Bridge device
07:00.0 - 10b5:8518 - Bridge device
08:00.0 - 1957:0040 - Processor
07:01.0 - 10b5:8518 - Bridge device
09:00.0 - 10b5:8112 - Bridge device
07:02.0 - 10b5:8518 - Bridge device
PCIE1: Bus 00 - 0b
PCIE2: connected as Root Complex
0d:00.0 - 1957:0040 - Processor
PCIE2: Bus 0c - 0d
This information is useful, but its difficult to determine the PCI bus
topology. To things clearer, we can use indention to make it more
obvious how the PCI bus is organized. For the example above, the
updated output with this change is:
In the examples above, an MPC8640 is connected to a PEX8518 PCIe switch
(01:00 and 02:0x), which is connected to another PEX8518 PCIe switch
(06:00 and 07:0x), which then connects to a MPC8572 processor (08:00).
Also, the MPC8640's PEX8518 PCIe switch is connected to a PCI ethernet
card (04:01) via a PEX8112 PCIe-to-PCI bridge (03:00).
Peter Tyser [Fri, 29 Oct 2010 22:59:28 +0000 (17:59 -0500)]
pci: Fix ordering of devices when CONFIG_PCI_SCAN_SHOW
Move the printing of PCI device information to before the PCI device is
configured. This prevents the case where recursive scanning results in
the deepest devices being printed first.
This change also makes PCI lockups during enumeration easier to
diagnose since the device that is being configured is printed out prior
to configuration. Previously, it was not possible to determine which
device caused the PCI lockup.
projects / u-boot / log